The second workshop on Intelligent Cross-Data Analysis and Retrieval – ICMR 2021
deadline: extended to 25th April, 2021
Call for papers
People can currently collect data from themselves and their surrounding environment quickly due to the exponential development of sensors, communication technologies, and social networks. Besides, data has evolved and become more intelligent than ever. Thanks to artificial intelligence and advanced application techniques, data can now be presented in meaningful forms that provide more information and knowledge for other near-human cognitive analytics and retrieval. The ability to collect such (intelligent) data opens the new opportunity to understand better the association between human beings and the surrounding environment's properties (i.e., humans as the center). These associations can be utilized for intelligence, planning, controlling, retrieval, and decision making efficiently and effectively by governments, industries, and citizens. Wearable sensors, lifelog cameras, and social networks can report people's health, activities, and behaviors from the first-view perspective. In contrast, surrounding sensors, social network interaction, and third-party data can give the third-view perspective of how their society activities look like. Several investigations have been done to deal with each perspective, but few investigations focus on analyzing and retrieving cross-data from different perspectives to bring better benefits to human beings.
Multimedia analytics and retrieval have gained significant improvement within a decade. People can now extract more data insights precisely and quickly towards having many excellent applications serving human lives. Nevertheless, people create multimedia and other types of data that reflect the diverse perspectives of human lives. In other words, multimedia and other data types are just pieces of the puzzle of the world's pictures. Hence, it is necessary to assembly all these pieces towards having a better solution for human-centered problems. Hence, the workshop welcomes those who work with multimedia and others and come from diverse research domains and disciplines to work on intelligent cross-data analytics and retrieval to bring a smart, sustainable society to human beings. The research domain can vary from well-being, disaster prevention, and mitigation, mobility to food computing, to name a few.
– Example topics of interest include but is not limited to the following
– Event-based cross-data retrieval
– Data mining and AI technology to discover and predict spatial-temporal-semantic correlations between cross-data.
– Complex event processing for linking sensors data from individuals, regions to broad areas dynamically.
– Transfer Learning from one region to another region to construct or customize similar analysis and predict events using locally collected data effectively and efficiently.
– Hypotheses Development of the associations within the heterogeneous data contributes towards building good multimodal models that make it possible to understand the impact of the surrounding environment on human beings at the local and individual scale.
– Realization of a prosperous and independent region in which people and nature coexist.
– Applications leverage intelligent cross-data analysis for a particular domain.
– Cross-datasets for Repeatable Experimentation.
– Federated Analytics and Federated Learning for cross-data.
– Privacy-public data collaboration.
Objectives
Followed by the success of the ICMR 2020 first workshop on intelligent cross-data analytics and retrieval, the second ICDAR workshop aims to provide the playground to people interested in the workshop's topics. In this playground, people share their experiences and brave new ideas towards making cross-data more intelligent by compensating each type of data's strengths and propose a new way to analyze and retrieve cross-data under different perspectives.
The accepted papers are expected to be published in the workshop proceedings. Excellent papers are encouraged to submit to journals or a special issue that the organizers will organize.
Paper Format
All papers must be formatted according to the ACM proceedings style. Click on the link (https://www.acm.org/publications/proceedings-template)to access Latex and Word templates for this format. Please use “sample-sigconf.tex” as a Latex template or “ACM_SigConf.doc” as a Word template. CCS code generation support tool is available here.
Length Of The Paper
We invite the following two types of papers: Full Paper: limited to 8 pages, including all text, figures, and references: Full Papers should describe original contents with evaluations. They will be reviewed by more than two experts based on:
- The originality of the content
- Quality of the content based on evaluation
- Relevance to the theme
- Clarity of the written presentation
Short Paper: limited to 4 pages, including all text, figures, and references. Short papers should describe work-in-progress as position papers. They will be reviewed by two experts based on:
- The originality of the content
- Relevance to the theme
- Clarity of the written presentation
April 27th, 2021
Daniela Lopez de Luise
April 27th, 2021
Daniela Lopez de Luise
Dear Colleagues,
We want to invite you to submit your latest research to the MDPI
Sustainability Journal, Special Issue on “Energy-Efficient Computing
Systems for Deep Learning” which is open for submissions until April 30,
2021.
https://www.mdpi.com/journal/sustainability/special_issues/Energy-Efficient_Computing
Deep learning (DL) is receiving much attention these days due to the
impressive performance achieved in a variety of application areas, such
as computer vision, natural language processing, machine translation,
and many more. Aimed at achieving ever-faster processing of these DL
workloads in an energy-efficient way, a myriad of specialized hardware
architectures (e.g., sparse tensor cores in NVIDIA A100 GPU) and
accelerators (e.g., Google TPU) are emerging. The goal is to provide
much higher performance-per-watt than general-purpose CPU processors.
Production deployments tend to have very high model complexity and
diversity, demanding solutions that can deliver higher productivity,
more powerful programming abstractions, more efficient software and
system architectures, faster runtime systems, and numerical libraries,
accompanied by a rich set of analysis tools.
DL models are generally memory and computationally intensive, for both
training and inference. Accelerating these operations in an
energy-efficient way has obvious advantages, first by reducing energy
consumption (e.g., data centers can consume megawatts, producing an
electricity bill similar to that of a small town), and secondly, by
making these models usable on smaller battery-operated devices at the
edge of the Internet. Edge devices run on strict power budgets and
highly constrained computing power. In addition, while deep neural
networks have motivated much of this effort, numerous applications and
models involve a wider variety of operations, network architectures, and
data processing. These applications and models are a challenge for
today’s computer architectures, system stacks, and programming
abstractions. As a result, non-von Neumann computing systems such as
those based on in-memory and/or in-network computing, which perform
specific computational tasks just where the data are generated, are
being investigated in order to avoid the latency of shuttling huge
amounts of data back and forth between processing and memory units.
Additionally, machine learning (ML) techniques are being explored to
reduce overall energy consumption in computing systems. These
applications of ML range from energy-aware scheduling algorithms in data
centers to battery life prediction techniques in edge devices. The high
level of interest in these areas calls for a dedicated journal issue to
discuss novel acceleration techniques and computation paradigms for
energy-efficient DL algorithms. Since the journal targets the
interaction of machine learning and computing systems, it will
complement other publications specifically focused on one of these two
parts in isolation.
The main objective of this Special Issue is to discuss and disseminate
the current work in this area, showcasing new and novel DL algorithms,
programming paradigms, software tools/libraries, and hardware
architectures oriented at providing energy efficiency, in particular
(but not limited to):
– Novel energy-efficient DL systems: heterogeneous multi/many-core
systems, GPUs, and FPGAs;
– Novel energy-efficient DL hardware accelerators and associated software;
– Emerging semiconductor technologies with applications to
energy-efficient DL hardware acceleration;
– Cloud and edge energy-efficient DL computing: hardware and software to
accelerate training and inference;
– In-memory computation and in-network computation for energy-efficient
DL processing;
– Machine-learning-based techniques for managing energy efficiency of
computing platforms.
Dr. José Cano
Dr. José L. Abellán
Prof. David Kaeli
Guest Editors
